A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions
Growth and expansion in construction has increased recently and especially in coastal areas. In Alexandria, Egypt, mega projects such as El-Max Port Project (Middle Port), Port of ABU QIR (EG AKI), hotels, and restaurants were spread along the coastal lines, thus, it will need a high electrical ener...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-03-01
|
Series: | Results in Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123023008617 |
_version_ | 1797247748594991104 |
---|---|
author | Mohamed K. Hassan H. Youssef Ibrahim M. Gaber Ahmed S. Shehata Youssef Khairy Alaa A. El-Bary |
author_facet | Mohamed K. Hassan H. Youssef Ibrahim M. Gaber Ahmed S. Shehata Youssef Khairy Alaa A. El-Bary |
author_sort | Mohamed K. Hassan |
collection | DOAJ |
description | Growth and expansion in construction has increased recently and especially in coastal areas. In Alexandria, Egypt, mega projects such as El-Max Port Project (Middle Port), Port of ABU QIR (EG AKI), hotels, and restaurants were spread along the coastal lines, thus, it will need a high electrical energy. Although, the great economic benefits of such projects, it will have some negative impacts, such as overloading on the present grid. According to recommendations of COP 27, Egypt is one of the countries targeting to increase the dependency on green energy to minimize the production of greenhouse gases. This study is interested in wave energy as a renewable source of energy. Using a machine learning model that predicts wave height and wave period through the year 2030 in three separate places (Alamein, Alexandria, and Mersa-Matruh), this study will try to estimate the future amount of wave energy along Egypt's coast. Hourly measurements of the significant height and the mean wave period for the period 1979–2023 have been utilized for this. An extractor for wave energy can also be built on the Overtopping Breakwater for Energy Conversion (OBREC) in order to use this energy to fill the hole in the electric grid. The machine learning model was developed using hourly wave height and period data from three buoys, and as a result, the results have a root mean square error (RMSE) of 0.52. The amount of energy taken, wave power, and system efficiency at each place were then fully determined using a mathematical model for each of the three locations. The area along the coast of Alamein had the highest energy extraction rates, followed by Alexandria and Mersa-Matruh in that order. The results of the mathematical model indicate that the yearly power generation for Alamein, Alexandria, and Mersa-Matruh is 25287 MWhr, 14713 MWhr, and 4865 MWhr, respectively. |
first_indexed | 2024-03-08T12:52:29Z |
format | Article |
id | doaj.art-82cd1d8bb09149289101e11c66bdfdf5 |
institution | Directory Open Access Journal |
issn | 2590-1230 |
language | English |
last_indexed | 2024-04-24T20:03:38Z |
publishDate | 2024-03-01 |
publisher | Elsevier |
record_format | Article |
series | Results in Engineering |
spelling | doaj.art-82cd1d8bb09149289101e11c66bdfdf52024-03-24T07:00:25ZengElsevierResults in Engineering2590-12302024-03-0121101734A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regionsMohamed K. Hassan0H. Youssef1Ibrahim M. Gaber2Ahmed S. Shehata3Youssef Khairy4Alaa A. El-Bary5Mechanical Engineering Department, College of Engineering and Islamic Architecture, Umm Al-Qura University, Makkah, 21955, Saudi ArabiaMechanical Engineering Department, College of Engineering and Islamic Architecture, Umm Al-Qura University, Makkah, 21955, Saudi ArabiaElectrical and Control Engineering Department, College of Engineering and Technology, Arab Academy for Science Technology and Maritime Transport, Alexandria, B.O. Box 1029, EgyptMarine Engineering Department, College of Engineering and Technology, Arab Academy for Science Technology and Maritime Transport, Alexandria, B.O. Box 1029, Egypt; Corresponding author.Construction & Building Engineering Department, College of Engineering and Technology, Arab Academy for Science Technology and Maritime Transport, Alexandria, B.O. Box 1029, EgyptBasic and Applied Science Institute, Arab Academy for Science, Technology and Maritime Transport, P.O. Box 1029, Alexandria, Egypt; National Committee for Mathematics, Academy of Scientific Research and Technology, Egypt; Council of Future Studies and Risk Management, Academy of Scientific Research and Technology, EgyptGrowth and expansion in construction has increased recently and especially in coastal areas. In Alexandria, Egypt, mega projects such as El-Max Port Project (Middle Port), Port of ABU QIR (EG AKI), hotels, and restaurants were spread along the coastal lines, thus, it will need a high electrical energy. Although, the great economic benefits of such projects, it will have some negative impacts, such as overloading on the present grid. According to recommendations of COP 27, Egypt is one of the countries targeting to increase the dependency on green energy to minimize the production of greenhouse gases. This study is interested in wave energy as a renewable source of energy. Using a machine learning model that predicts wave height and wave period through the year 2030 in three separate places (Alamein, Alexandria, and Mersa-Matruh), this study will try to estimate the future amount of wave energy along Egypt's coast. Hourly measurements of the significant height and the mean wave period for the period 1979–2023 have been utilized for this. An extractor for wave energy can also be built on the Overtopping Breakwater for Energy Conversion (OBREC) in order to use this energy to fill the hole in the electric grid. The machine learning model was developed using hourly wave height and period data from three buoys, and as a result, the results have a root mean square error (RMSE) of 0.52. The amount of energy taken, wave power, and system efficiency at each place were then fully determined using a mathematical model for each of the three locations. The area along the coast of Alamein had the highest energy extraction rates, followed by Alexandria and Mersa-Matruh in that order. The results of the mathematical model indicate that the yearly power generation for Alamein, Alexandria, and Mersa-Matruh is 25287 MWhr, 14713 MWhr, and 4865 MWhr, respectively.http://www.sciencedirect.com/science/article/pii/S2590123023008617Shore protectionCoastal protectionClimate changeWave energy extractorRenewable energySignificant wave height |
spellingShingle | Mohamed K. Hassan H. Youssef Ibrahim M. Gaber Ahmed S. Shehata Youssef Khairy Alaa A. El-Bary A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions Results in Engineering Shore protection Coastal protection Climate change Wave energy extractor Renewable energy Significant wave height |
title | A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions |
title_full | A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions |
title_fullStr | A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions |
title_full_unstemmed | A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions |
title_short | A predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions |
title_sort | predictive machine learning model for estimating wave energy based on wave conditions relevant to coastal regions |
topic | Shore protection Coastal protection Climate change Wave energy extractor Renewable energy Significant wave height |
url | http://www.sciencedirect.com/science/article/pii/S2590123023008617 |
work_keys_str_mv | AT mohamedkhassan apredictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT hyoussef apredictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT ibrahimmgaber apredictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT ahmedsshehata apredictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT youssefkhairy apredictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT alaaaelbary apredictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT mohamedkhassan predictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT hyoussef predictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT ibrahimmgaber predictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT ahmedsshehata predictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT youssefkhairy predictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions AT alaaaelbary predictivemachinelearningmodelforestimatingwaveenergybasedonwaveconditionsrelevanttocoastalregions |